Hugging Face's logo

Joy28
/
videomae-base-finetuned-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Joy28 commited on
Commit
bc27358
·
1 Parent(s): ce3eaac

Model save

Browse files
Files changed (2) hide show
  1. README.md +32 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5077
21
- - Accuracy: 0.8362
22
 
23
  ## Model description
24
 
@@ -38,31 +38,48 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
- - training_steps: 572
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.537 | 0.13 | 72 | 1.3526 | 0.3691 |
54
- | 1.3677 | 1.13 | 144 | 1.0690 | 0.6094 |
55
- | 1.0818 | 2.13 | 216 | 0.6865 | 0.8069 |
56
- | 1.1608 | 3.13 | 288 | 0.6642 | 0.7682 |
57
- | 0.9544 | 4.13 | 360 | 0.6866 | 0.7511 |
58
- | 0.896 | 5.13 | 432 | 0.5387 | 0.8112 |
59
- | 0.9193 | 6.13 | 504 | 0.5693 | 0.7897 |
60
- | 0.6941 | 7.12 | 572 | 0.4813 | 0.8541 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.35.2
66
  - Pytorch 1.13.1
67
- - Datasets 2.15.0
68
  - Tokenizers 0.15.0
 
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7174
21
+ - Accuracy: 0.6898
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 2925
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.6183 | 0.04 | 118 | 1.5576 | 0.4194 |
54
+ | 1.4874 | 1.04 | 236 | 1.3517 | 0.4240 |
55
+ | 1.6523 | 2.04 | 354 | 1.3001 | 0.3364 |
56
+ | 1.2763 | 3.04 | 472 | 1.1898 | 0.3917 |
57
+ | 1.2819 | 4.04 | 590 | 1.1945 | 0.5161 |
58
+ | 1.1196 | 5.04 | 708 | 0.9771 | 0.5668 |
59
+ | 1.1976 | 6.04 | 826 | 1.1079 | 0.4747 |
60
+ | 0.8174 | 7.04 | 944 | 0.8705 | 0.6636 |
61
+ | 0.7923 | 8.04 | 1062 | 0.7827 | 0.6636 |
62
+ | 0.6052 | 9.04 | 1180 | 0.9455 | 0.6313 |
63
+ | 0.7902 | 10.04 | 1298 | 0.9512 | 0.6175 |
64
+ | 0.9501 | 11.04 | 1416 | 0.8058 | 0.7373 |
65
+ | 1.1756 | 12.04 | 1534 | 0.7674 | 0.7327 |
66
+ | 0.8482 | 13.04 | 1652 | 0.8455 | 0.6866 |
67
+ | 0.7657 | 14.04 | 1770 | 0.9124 | 0.6820 |
68
+ | 0.9752 | 15.04 | 1888 | 0.9788 | 0.6313 |
69
+ | 0.7176 | 16.04 | 2006 | 0.6860 | 0.7604 |
70
+ | 0.7682 | 17.04 | 2124 | 0.8052 | 0.7143 |
71
+ | 0.8862 | 18.04 | 2242 | 0.9102 | 0.6820 |
72
+ | 0.6609 | 19.04 | 2360 | 0.9360 | 0.6866 |
73
+ | 0.9678 | 20.04 | 2478 | 0.8441 | 0.6866 |
74
+ | 0.8617 | 21.04 | 2596 | 0.8136 | 0.7097 |
75
+ | 0.7097 | 22.04 | 2714 | 0.8615 | 0.7005 |
76
+ | 0.5089 | 23.04 | 2832 | 0.7796 | 0.7005 |
77
+ | 0.715 | 24.03 | 2925 | 0.7685 | 0.7235 |
78
 
79
 
80
  ### Framework versions
81
 
82
+ - Transformers 4.36.2
83
  - Pytorch 1.13.1
84
+ - Datasets 2.16.1
85
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdc42918434c143f320b5431a5213b315a4ed6aa438a5a59072acc0705f9c1b8
3
  size 344946604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc9ad463c38b11c6ed7b5da27678cc7bd0c94bf30ec59ff22cc03ffcc57f33e
3
  size 344946604